Server Quality Checklist

Tool Scores

• fragrance_infoA
  3.6/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the burden. It discloses the returned data fields (brand, year, gender, etc.) but does not mention error handling, invalid slug behavior, or any rate limits. For a read-only retrieval tool, the transparency is acceptable but not rich.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, well-structured sentence that front-loads the core purpose and enumerates the return fields efficiently. No wasted words or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with one parameter and no output schema, the description lists all relevant return categories, providing a complete picture of what the tool does. The lack of error behavior is a minor gap given the simplicity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already describes the slug parameter with 100% coverage, including an example. The description adds only 'by its slug', which is redundant. Since schema coverage is full, baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool returns a full fragrance profile by slug, listing specific data fields. It distinguishes itself from siblings by focusing on profile retrieval rather than search or dupes, though it lacks an explicit verb like 'retrieves' or 'gets'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Usage is implied: the slug parameter description notes it comes from search_fragrance, indicating a workflow. However, there is no explicit when-to-use vs. alternatives (e.g., when not to use find_dupes) or exclusion statements.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• find_dupesA
  4/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full burden of behavioral disclosure. It adds meaningful context by specifying the matching mechanism ('distinctive-note overlap') and the output format ('similarity ranking'). This goes beyond the bare function, though it could be more explicit about limitations or data coverage.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is highly concise, consisting of two sentences that front-load the core purpose and immediately explain the return type. There is no unnecessary verbiage; every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with one parameter, no annotations, and no output schema, the description covers the essential aspects: what it finds, the method, and the ranking behavior. However, since there is no output schema, it leaves some ambiguity about the exact structure of 'matches' (e.g., whether it returns fragrance slugs, names, scores). Still, it is sufficiently informative for an agent to rely on.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already provides full coverage of the single parameter (slug) with an example. The description does not add additional meaning beyond referring to the fragrance as 'a given one,' which is redundant. Baseline of 3 is appropriate because the schema does all necessary work.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: find fragrances that smell similar to a given one, using a specific method (distinctive-note overlap). This is a specific verb+resource+method that distinguishes it from the sibling tools (search_fragrance, fragrance_info).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use the tool (when the user wants similar fragrances to a known one) but does not explicitly mention alternatives or exclusions. It does not say 'use search_fragrance for general search' or 'use fragrance_info for details,' so the guidance is purely contextual without direct sibling differentiation.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• search_fragranceA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description bears full responsibility and partially fulfills it by disclosing the return type: 'matching fragrances, brands, notes and perfumers with links.' It lacks details on pagination or rate limits, but the read-only nature is implied by 'Search' and 'Returns,' which is sufficient for a simple search tool.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, front-loaded sentence that states the verb and resource immediately, then adds return details. Every word contributes meaning, with no redundancy or padding.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a one-parameter search tool with no output schema, the description covers input and output adequately. It tells users what they can search and what they will get, but it could be more complete by explicitly mentioning alternatives to sibling tools or noting any result limits.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has 100% coverage for the single 'query' parameter, but the description adds meaningful semantics by specifying that the query can match name, brand, note, or perfumer. This goes beyond the schema's terse examples and clarifies the intended search scope.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's action ('Search') and resource ('the parfica.com fragrance encyclopedia'), and specifies the search criteria (by name, brand, note or perfumer). It naturally distinguishes itself from sibling tools like fragrance_info (specific fragrance info) and find_dupes (dupe finding) by focusing on cross-entity search.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use it: whenever you need to search across the encyclopedia by various criteria. However, it does not explicitly contrast with sibling tools or state when not to use it, leaving some ambiguity about how it complements fragrance_info or find_dupes.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.